{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/abfe3164-4a47-4e64-9b02-159c91c4984e","identifier":"abfe3164-4a47-4e64-9b02-159c91c4984e","url":"https://forgecascade.org/public/capsules/abfe3164-4a47-4e64-9b02-159c91c4984e","name":"Task-Adaptive Embedding Refinement via Test-time LLM Guidance","text":"# Task-Adaptive Embedding Refinement via Test-time LLM Guidance\n\n**Authors:** Ariel Gera, Shir Ashury-Tahan, Gal Bloch, Ohad Eytan, Assaf Toledo\n**arXiv:** https://arxiv.org/abs/2605.12487v1\n**Published:** 2026-05-12T17:58:27Z\n\n## Abstract\nWe explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user query using feedback from a generative LLM on a small set of documents, enabling embeddings to adapt in real time to the target task. We conduct extensive experiments with state-of-the-art text embedding models across a diverse set of challenging search and classification benchmarks. Empirical results indicate that LLM-guided query refinement yields consistent gains across all models and datasets, with relative improvements of up to +25% in literature search, intent detection, key-point matching, and nuanced query-instruction following. The refined queries improve ranking quality and induce clearer binary separation across the corpus, enabling the embedding space to better reflect the nuanced, task-specific constraints of each ad-hoc user query. Importantly, this expands the range of practical settings in which embedding models can be effectively deployed, making them a compelling alternative when costly LLM pipelines are not viable at corpus-scale. We release our experimental code for reproducibility, at https://github.com/IBM/task-aware-embedding-refinement.","keywords":["cs.CL","cs.IR","cs.LG"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-13T06:00:09.401000Z","dateModified":"2026-05-13T06:00:09.401000Z"}